This paper assesses trending AI foundation models, especially emerging computer vision foundation models and their performance in natural landscape feature segmentation. While the term foundation model has quickly garnered interest from the geospatial domain, its definition remains vague. Hence, this paper will first introduce AI foundation models and their defining characteristics. Built upon the tremendous success achieved by Large Language Models (LLMs) as the foundation models for language tasks, this paper discusses the challenges of building foundation models for geospatial artificial intelligence (GeoAI) vision tasks. To evaluate the performance of large AI vision models, especially Meta’s Segment Anything Model (SAM), we implemented different instance segmentation pipelines that minimize the changes to SAM to leverage its power as a foundation model. A series of prompt strategies were developed to test SAM’s performance regarding its theoretical upper bound of predictive accuracy, zero-shot performance, and domain adaptability through fine-tuning. The analysis used two permafrost feature datasets, ice-wedge polygons and retrogressive thaw slumps because (1) these landform features are more challenging to segment than man-made features due to their complicated formation mechanisms, diverse forms, and vague boundaries; (2) their presence and changes are important indicators for Arctic warming and climate change. The results show that although promising, SAM still has room for improvement to support AI-augmented terrain mapping. The spatial and domain generalizability of this finding is further validated using a more general dataset EuroCrops for agricultural field mapping. Finally, we discuss future research directions that strengthen SAM’s applicability in challenging geospatial domains.

Vision foundation models are a new frontier in Geospatial Artificial Intelligence (GeoAI), an interdisciplinary research area that applies and extends AI for geospatial problem solving and geographic knowledge discovery, because of their potential to enable powerful image analysis by learning and extracting important image features from vast amounts of geospatial data. This paper evaluates the performance of the first-of-its-kind geospatial foundation model, IBM-NASA's Prithvi, to support a crucial geospatial analysis task: flood inundation mapping. This model is compared with convolutional neural network and vision transformer-based architectures in terms of mapping accuracy for flooded areas. A benchmark dataset, Sen1Floods11, is used in the experiments, and the models' predictability, generalizability, and transferability are evaluated based on both a test dataset and a dataset that is completely unseen by the model. Results show the good transferability of the Prithvi model, highlighting its performance advantages in segmenting flooded areas in previously unseen regions. The findings also indicate areas for improvement for the Prithvi model in terms of adopting multi-scale representation learning, developing more end-to-end pipelines for high-level image analysis tasks, and offering more flexibility in terms of input data bands.

This article introduces our research in developing a probabilistic model to extract linear terrain features from high resolution Digital Elevation Models (DEMs). The proposed model takes full advantage of spatio-contextual information to characterize terrain changes. It first derives a quantifiable measure of spatio-contextual patterns of linear terrain features, such as ridgelines, valley lines and crater boundaries, and then adopts multiple neighborhood analysis and a probability model to address data uncertainty in terrain surface modeling. Different from traditional approaches, the proposed model has the ability to achieve near-automated processing. It also supports effective extraction of terrain features in both smooth and rough surfaces. Through a series of experiments, we demonstrate that the proposed approach outperforms existing techniques, including thresholding, stream/drainage network analysis, visual descriptor detection, object-based image analysis and edge detection. This work contributes to both the geospatial data science and geomorphology communities with a new way of utilizing high-resolution imagery in terrain analysis.

Recent advancements in artificial intelligence (AI) and deep learning enable more accurate, scalable, and automated mapping. This paper provides a comprehensive review of the applications of AI, particularly deep learning, in landslide inventory mapping. In addition to examining commonly used data sources and model architectures, we explore innovative strategies such as feature enhancement and fusion, attention-boosted techniques, and advanced learning approaches, including active learning and transfer learning, to enhance model adaptability and predictability. We also highlight the remaining challenges and potential research directions, including the estimation of more diverse variables in landslide mapping, multimodal data alignment, modeling regional variability and replicability, as well as issues related to data misinterpretation and model explainability. This review aims to serve as a useful resource for researchers and practitioners, promoting the integration of deep learning into landslide research and disaster management.